default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDQiongkai Xu
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[c32]Zihan Zhu, Qiongkai Xu, Amin Beheshti:
HEAL: Healthcare Emergency Assistants Leveraging Large Language Models. WWW (Companion Volume) 2025: 2959-2962- [i30]Yiyi Chen, Qiongkai Xu, Johannes Bjerva:
ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation. CoRR abs/2502.11308 (2025) - [i29]Weijun Li, Ansh Arora, Xuanli He, Mark Dras, Qiongkai Xu:
Defending Deep Neural Networks against Backdoor Attacks via Module Switching. CoRR abs/2504.05902 (2025) - 2024
- [j1]Xuanli He, Qiongkai Xu
, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn:
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks. Trans. Assoc. Comput. Linguistics 12: 996-1010 (2024) - [c31]Anudeex Shetty, Yue Teng, Ke He, Qiongkai Xu:
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection. ACL (1) 2024: 13430-13444 - [c30]Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, Qiongkai Xu:
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge. ACL (Findings) 2024: 15059-15075 - [c29]Weijun Li, Qiongkai Xu, Mark Dras:
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients. EMNLP 2024: 4786-4798 - [c28]Jun Wang, Qiongkai Xu, Xuanli He, Benjamin I. P. Rubinstein, Trevor Cohn:
Backdoor Attacks on Multilingual Machine Translation. NAACL-HLT 2024: 4515-4534 - [i28]Aditya Desu, Xuanli He, Qiongkai Xu, Wei Lu:
Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation. CoRR abs/2402.16889 (2024) - [i27]Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, Qiongkai Xu:
Here's a Free Lunch: Sanitizing Backdoored Models with Model Merge. CoRR abs/2402.19334 (2024) - [i26]Anudeex Shetty, Yue Teng, Ke He, Qiongkai Xu:
WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection. CoRR abs/2403.01472 (2024) - [i25]Jun Wang, Qiongkai Xu, Xuanli He, Benjamin I. P. Rubinstein, Trevor Cohn:
Backdoor Attack on Multilingual Machine Translation. CoRR abs/2404.02393 (2024) - [i24]Wanru Zhao, Vidit Khazanchi, Haodi Xing, Xuanli He, Qiongkai Xu, Nicholas Donald Lane:
Attacks on Third-Party APIs of Large Language Models. CoRR abs/2404.16891 (2024) - [i23]Xuanli He, Jun Wang, Qiongkai Xu, Pasquale Minervini, Pontus Stenetorp, Benjamin I. P. Rubinstein, Trevor Cohn:
Transferring Troubles: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning. CoRR abs/2404.19597 (2024) - [i22]Xuanli He, Qiongkai Xu, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn:
SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks. CoRR abs/2405.11575 (2024) - [i21]Weijun Li, Qiongkai Xu, Mark Dras:
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients. CoRR abs/2406.00999 (2024) - [i20]Shuo Huang, William MacLean, Xiaoxi Kang, Anqi Wu, Lizhen Qu, Qiongkai Xu, Zhuang Li, Xingliang Yuan, Gholamreza Haffari:
NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human. CoRR abs/2406.03749 (2024) - [i19]Pedro Faustini, Shakila Mahjabin Tonni, Annabelle McIver, Qiongkai Xu, Mark Dras:
IDT: Dual-Task Adversarial Attacks for Privacy Protection. CoRR abs/2406.19642 (2024) - [i18]Anudeex Shetty, Qiongkai Xu, Jey Han Lau:
WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks. CoRR abs/2409.04459 (2024) - [i17]Diego Mollá, Qiongkai Xu, Zijie Zeng, Zhuang Li:
Overview of the 2024 ALTA Shared Task: Detect Automatic AI-Generated Sentences for Human-AI Hybrid Articles. CoRR abs/2412.17848 (2024) - [i16]Yao Tong, Weijun Li, Xuanli He, Haolan Zhan, Qiongkai Xu:
Cut the Deadwood Out: Post-Training Model Purification with Selective Module Substitution. CoRR abs/2412.20476 (2024) - 2023
- [c27]Terry Yue Zhuo, Qiongkai Xu, Xuanli He, Trevor Cohn:
Rethinking Round-Trip Translation for Machine Translation Evaluation. ACL (Findings) 2023: 319-337 - [c26]Diego Mollá, Haolan Zhan, Xuanli He, Qiongkai Xu:
Overview of the 2023 ALTA Shared Task: Discriminate between Human-Written and Machine-Generated Text. ALTA 2023: 148-152 - [c25]Qiongkai Xu, Trevor Cohn, Olga Ohrimenko:
Fingerprint Attack: Client De-Anonymization in Federated Learning. ECAI 2023: 2792-2801 - [c24]Fan Jiang, Qiongkai Xu, Tom Drummond, Trevor Cohn:
Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval. EMNLP (Findings) 2023: 912-931 - [c23]Xuanli He, Qiongkai Xu, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn:
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation. EMNLP 2023: 953-967 - [c22]Qiongkai Xu, Christian Walder, Chenchen Xu:
Humanly Certifying Superhuman Classifiers. ICLR 2023 - [c21]Yujin Huang, Terry Yue Zhuo, Qiongkai Xu, Han Hu, Xingliang Yuan, Chunyang Chen:
Training-free Lexical Backdoor Attacks on Language Models. WWW 2023: 2198-2208 - [i15]Yujin Huang, Terry Yue Zhuo, Qiongkai Xu, Han Hu, Xingliang Yuan, Chunyang Chen:
Training-free Lexical Backdoor Attacks on Language Models. CoRR abs/2302.04116 (2023) - [i14]Xuanli He, Qiongkai Xu, Jun Wang, Benjamin I. P. Rubinstein, Trevor Cohn:
Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation. CoRR abs/2305.11596 (2023) - [i13]Qiongkai Xu, Trevor Cohn, Olga Ohrimenko:
Fingerprint Attack: Client De-Anonymization in Federated Learning. CoRR abs/2310.05960 (2023) - [i12]Fan Jiang, Qiongkai Xu, Tom Drummond, Trevor Cohn:
Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval. CoRR abs/2311.15564 (2023) - 2022
- [c20]Xuanli He, Qiongkai Xu, Lingjuan Lyu, Fangzhao Wu, Chenguang Wang:
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark. AAAI 2022: 10758-10766 - [c19]Qiongkai Xu, Xuanli He, Lingjuan Lyu, Lizhen Qu, Gholamreza Haffari:
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs. COLING 2022: 2849-2860 - [c18]Xuanli He, Lingjuan Lyu, Chen Chen, Qiongkai Xu:
Extracted BERT Model Leaks More Information than You Think! EMNLP 2022: 1530-1537 - [c17]Zhuang Li, Lizhen Qu, Qiongkai Xu, Tongtong Wu, Tianyang Zhan, Gholamreza Haffari:
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation. EMNLP 2022: 10335-10356 - [c16]Xuanli He, Qiongkai Xu, Yi Zeng, Lingjuan Lyu, Fangzhao Wu, Jiwei Li, Ruoxi Jia:
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks. NeurIPS 2022 - [i11]Zhuang Li, Lizhen Qu, Qiongkai Xu, Tongtong Wu, Tianyang Zhan, Gholamreza Haffari:
Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation. CoRR abs/2202.13363 (2022) - [i10]Terry Yue Zhuo, Qiongkai Xu, Xuanli He, Trevor Cohn:
Rethinking Round-trip Translation for Automatic Machine Translation Evaluation. CoRR abs/2209.07351 (2022) - [i9]Xuanli He, Qiongkai Xu, Yi Zeng, Lingjuan Lyu, Fangzhao Wu, Jiwei Li, Ruoxi Jia:
CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks. CoRR abs/2209.08773 (2022) - [i8]Xuanli He, Chen Chen, Lingjuan Lyu, Qiongkai Xu:
Extracted BERT Model Leaks More Information than You Think! CoRR abs/2210.11735 (2022) - 2021
- [c15]Xuanli He, Lingjuan Lyu, Lichao Sun, Qiongkai Xu:
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable! NAACL-HLT 2021: 2006-2012 - [c14]Qiongkai Xu, Chenchen Xu, Lizhen Qu:
Privacy Monitoring Service for Conversations. WSDM 2021: 1093-1096 - [i7]Xuanli He, Lingjuan Lyu, Qiongkai Xu, Lichao Sun:
Model Extraction and Adversarial Transferability, Your BERT is Vulnerable! CoRR abs/2103.10013 (2021) - [i6]Qiongkai Xu, Xuanli He, Lingjuan Lyu, Lizhen Qu, Gholamreza Haffari:
Beyond Model Extraction: Imitation Attack for Black-Box NLP APIs. CoRR abs/2108.13873 (2021) - [i5]Qiongkai Xu, Christian Walder, Chenchen Xu:
Humanly Certifying Superhuman Classifiers. CoRR abs/2109.07867 (2021) - [i4]Xuanli He, Qiongkai Xu, Lingjuan Lyu, Fangzhao Wu, Chenguang Wang:
Protecting Intellectual Property of Language Generation APIs with Lexical Watermark. CoRR abs/2112.02701 (2021) - 2020
- [c13]Yolande A. A. Strengers, Lizhen Qu, Qiongkai Xu, Jarrod Knibbe:
Adhering, Steering, and Queering: Treatment of Gender in Natural Language Generation. CHI 2020: 1-14 - [c12]Qiongkai Xu, Lizhen Qu, Zeyu Gao, Gholamreza Haffari:
Personal Information Leakage Detection in Conversations. EMNLP (1) 2020: 6567-6580
2010 – 2019
- 2019
- [c11]Qiongkai Xu, Chenchen Xu, Lizhen Qu:
ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation. EMNLP/IJCNLP (3) 2019: 13-18 - [c10]Qiongkai Xu, Lizhen Qu, Chenchen Xu, Ran Cui:
Privacy-Aware Text Rewriting. INLG 2019: 247-257 - [i3]Qiongkai Xu, Chenchen Xu, Lizhen Qu:
ALTER: Auxiliary Text Rewriting Tool for Natural Language Generation. CoRR abs/1909.06564 (2019) - 2018
- [c9]Liyuan Zhou, Qiongkai Xu, Hanna Suominen, Tom Gedeon:
EPUTION at SemEval-2018 Task 2: Emoji Prediction with User Adaption. SemEval@NAACL-HLT 2018: 449-453 - [i2]Qiongkai Xu, Juyan Zhang, Lizhen Qu, Lexing Xie, Richard Nock:
D-PAGE: Diverse Paraphrase Generation. CoRR abs/1808.04364 (2018) - 2017
- [c8]Sunghwan Mac Kim, Qiongkai Xu, Lizhen Qu, Stephen Wan, Cécile Paris:
Demographic Inference on Twitter using Recursive Neural Networks. ACL (2) 2017: 471-477 - [c7]Qiongkai Xu, Qing Wang, Chenchen Xu, Lizhen Qu:
Attentive Graph-based Recursive Neural Network for Collective Vertex Classification. CIKM 2017: 2403-2406 - [i1]Qiongkai Xu, Qing Wang, Chenchen Xu, Lizhen Qu:
Collective Vertex Classification Using Recursive Neural Network. CoRR abs/1701.06751 (2017) - 2016
- [c6]Shaosheng Cao, Wei Lu, Qiongkai Xu:
Deep Neural Networks for Learning Graph Representations. AAAI 2016: 1145-1152 - [c5]Zhuang Li, Lizhen Qu, Qiongkai Xu, Mark Johnson:
Unsupervised Pre-training With Seq2Seq Reconstruction Loss for Deep Relation Extraction Models. ALTA 2016: 54-64 - [c4]Yuan Ni, Qiongkai Xu, Feng Cao, Yosi Mass, Dafna Sheinwald, Huijia Zhu, Shao Sheng Cao:
Semantic Documents Relatedness using Concept Graph Representation. WSDM 2016: 635-644 - 2015
- [c3]Qiongkai Xu, Albert Chen, Chang Li:
Detecting English-French Cognates Using Orthographic Edit Distance. ALTA 2015: 145-149 - [c2]Shaosheng Cao, Wei Lu, Qiongkai Xu:
GraRep: Learning Graph Representations with Global Structural Information. CIKM 2015: 891-900 - 2012
- [c1]Qiongkai Xu, Hai Zhao:
Using Deep Linguistic Features for Finding Deceptive Opinion Spam. COLING (Posters) 2012: 1341-1350
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2025-05-27 23:16 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
